tiennvcs commited on
Commit
50c10b2
1 Parent(s): de796df

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-base-uncased-finetuned-docvqa
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-base-uncased-finetuned-docvqa
14
+
15
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.9146
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
+ - seed: 250500
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 2.2151 | 0.1 | 1000 | 2.6299 |
49
+ | 1.8885 | 0.21 | 2000 | 2.2217 |
50
+ | 1.7353 | 0.31 | 3000 | 2.1675 |
51
+ | 1.6188 | 0.41 | 4000 | 2.2436 |
52
+ | 1.5802 | 0.52 | 5000 | 2.0539 |
53
+ | 1.4875 | 0.62 | 6000 | 2.0551 |
54
+ | 1.4675 | 0.73 | 7000 | 1.9368 |
55
+ | 1.3485 | 0.83 | 8000 | 1.9456 |
56
+ | 1.3273 | 0.93 | 9000 | 1.9281 |
57
+ | 1.1048 | 1.04 | 10000 | 1.9333 |
58
+ | 0.9529 | 1.14 | 11000 | 2.2019 |
59
+ | 0.9418 | 1.24 | 12000 | 2.0381 |
60
+ | 0.9209 | 1.35 | 13000 | 1.8753 |
61
+ | 0.8788 | 1.45 | 14000 | 1.9964 |
62
+ | 0.8729 | 1.56 | 15000 | 1.9690 |
63
+ | 0.8671 | 1.66 | 16000 | 1.8513 |
64
+ | 0.8379 | 1.76 | 17000 | 1.9627 |
65
+ | 0.8722 | 1.87 | 18000 | 1.8988 |
66
+ | 0.7842 | 1.97 | 19000 | 1.9146 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.11.3
72
+ - Pytorch 1.9.0+cu111
73
+ - Datasets 1.14.0
74
+ - Tokenizers 0.10.3